Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    pronouns and words related to actions and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    417
    -0.17
    каз
    -0.16
    âĻª
    -0.15
     behaviours
    -0.15
    017
    -0.14
    à¸ŀร
    -0.14
    nÃŃ
    -0.14
    cs
    -0.14
    invalidate
    -0.14
    /tos
    -0.14
    POSITIVE LOGITS
    StackTrace
    0.16
    groupid
    0.14
    abbage
    0.14
    ãĤ´ãĥª
    0.14
    ุà¸Ĺà¸ĺ
    0.14
    guild
    0.14
    imized
    0.14
    Æ¡m
    0.14
    InParameter
    0.13
    ̣
    0.13
    Act Density 0.000%

    No Known Activations